Proposta de um Descritor Híbrido para Aprimoramento da Identificação Automática de Melanoma
Resumo
O melanoma é o câncer de pele com alto grau de mortalidade. Estima-se para 2017 que 9.730 pessoas morrerão de melanoma nos EUA. Contudo, a detecção precoce da doença reduz a taxa de mortalidade drasticamente. Desse modo, esse trabalho tem como objetivo propor um descritor híbrido para extração de características na detecção do melanoma. Diversos métodos foram propostos, porém, em sua maioria utilizam características de um único descritor. Assim, foi realizada a combinação dos principais descritores e uma seleção de 10% dos atributos mais relevantes com o Gain Ratio Information. Os resultados obtidos provam que o método é eficiente, atingindo uma acurácia de 95,5% (na base PH2) e 84,9% (na base DermIS) com o MultiLayer Perceptron.
Referências
Al-Akaidi, M. (2004). Fractal speech processing. Cambridge university press.
Araujo, A. F. et al. (2012). Análise e caracterização de lesões de pele para auxílio ao diagnóstico médico. Avanços em Visão Computacional.
Bhati, P. e Singhal, M. (2015). Early stage detection and classification of melanoma. In Communication, Control and Intelligent Systems (CCIS), 2015, pages 181–185. IEEE.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.
Chang, W.-Y. et al. (2013). Computer-aided diagnosis of skin lesions using conventional digital photography: a reliability and feasibility study. PloS one, 8(11):e76212.
Chu, A., Sehgal, C. M., e Greenleaf, J. F. (1990). Use of gray value distribution of run lengths for texture analysis. Pattern Recognition Letters, 11(6):415–419.
Codella, N., Cai, J., et al. (2015). Deep learning, sparse coding, and svm for melanoma recognition in dermoscopy images. In International Workshop on Machine Learning in Medical Imaging, pages 118–126. Springer.
Cortes, C. e Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3):273–297.
Dalal, N. e Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 886–893. IEEE.
Dasarathyand, B. R. e Holder, E. B. (1991). Image characterizations based on joint gray-level run-length distributions. Pattern Recognition Letters, 12(8):497–502.
Diepgen, T. L. e Yihune, G. (2012). Dermatology information system – dermis. [link]. Acessado em: 2017.
Galloway, M. M. (1975). Texture analysis using gray level run lengths. Computer graphics and image processing, 4(2):172–179.
Haralick, R. M., Shanmugam, K., et al. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, 3(6):610–621.
Haykin, S. S. (2009). Neural networks and learning machines, volume 3. Pearson Upper Saddle River, NJ, USA:.
INCA (2016). Tipo - pele melanoma. [link]. Acessado em: 2017.
Kumar, A. et al. (2016). An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE Journal of Biomedical and Health Informatics.
Lacy, K. e Alwan, W. (2013). Skin cancer. Medicine, 41(7):402–405.
Landis, J. R. e Koch, G. G. (1977). The measurement of observer agreement for categorical data. biometrics, pages 159–174.
Mendonça, T. et al. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, pages 5437–5440. IEEE.
Moura, N. H. et al. (2015). Classificação de lesões de pele utilizando atributos de cor e textura. Workshop de Informática Médica – WIM.
Ojala, T., Pietikäinen, M., e Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51–59.
Oliveira, R. B. et al. (2016). A computational approach for detecting pigmented skin lesions in macroscopic images. Expert Systems with Applications, 61:53–63.
Rosenfield, G. H. e Fitzpatrick-Lins, K. (1986). A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric engineering and remote sensing, 52(2):223–227.
Sánchez-Monedero, J. et al. (2016). Classification of melanoma presence and thickness based on computational image analysis. In International Conference on Hybrid Artificial Intelligence Systems, pages 427–438. Springer.
Shin, H.-C., Roth, H. R., et al. (2016). Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning. IEEE transactions on medical imaging, 35(5):1285–1298.
Silva Júnior, E. R. (2007). Investigação de técnicas de extração e seleção de características e classificadores aplicados ao problema de classificação de dígitos manuscritos de imagens de documentos históricos. 51 f. Monografia (Bacharelado em Engenharia da Computação) — Escola Politécnica de Pernambuco, UFPE, Pernambuco.
Sobel, I. (1970). Camera models and machine perception. Technical report, DTIC Document.
Society, A. C. (2015). Cancer facts & figures 2015. [link]. Acessado em: 2017.
Tamura, H., Mori, S., e Yamawaki, T. (1978). Textural features corresponding to visual perception. IEEE Transactions on Systems, Man, and Cybernetics, 8(6):460–473.
Araujo, A. F. et al. (2012). Análise e caracterização de lesões de pele para auxílio ao diagnóstico médico. Avanços em Visão Computacional.
Bhati, P. e Singhal, M. (2015). Early stage detection and classification of melanoma. In Communication, Control and Intelligent Systems (CCIS), 2015, pages 181–185. IEEE.
Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.
Chang, W.-Y. et al. (2013). Computer-aided diagnosis of skin lesions using conventional digital photography: a reliability and feasibility study. PloS one, 8(11):e76212.
Chu, A., Sehgal, C. M., e Greenleaf, J. F. (1990). Use of gray value distribution of run lengths for texture analysis. Pattern Recognition Letters, 11(6):415–419.
Codella, N., Cai, J., et al. (2015). Deep learning, sparse coding, and svm for melanoma recognition in dermoscopy images. In International Workshop on Machine Learning in Medical Imaging, pages 118–126. Springer.
Cortes, C. e Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3):273–297.
Dalal, N. e Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 886–893. IEEE.
Dasarathyand, B. R. e Holder, E. B. (1991). Image characterizations based on joint gray-level run-length distributions. Pattern Recognition Letters, 12(8):497–502.
Diepgen, T. L. e Yihune, G. (2012). Dermatology information system – dermis. [link]. Acessado em: 2017.
Galloway, M. M. (1975). Texture analysis using gray level run lengths. Computer graphics and image processing, 4(2):172–179.
Haralick, R. M., Shanmugam, K., et al. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, 3(6):610–621.
Haykin, S. S. (2009). Neural networks and learning machines, volume 3. Pearson Upper Saddle River, NJ, USA:.
INCA (2016). Tipo - pele melanoma. [link]. Acessado em: 2017.
Kumar, A. et al. (2016). An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE Journal of Biomedical and Health Informatics.
Lacy, K. e Alwan, W. (2013). Skin cancer. Medicine, 41(7):402–405.
Landis, J. R. e Koch, G. G. (1977). The measurement of observer agreement for categorical data. biometrics, pages 159–174.
Mendonça, T. et al. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, pages 5437–5440. IEEE.
Moura, N. H. et al. (2015). Classificação de lesões de pele utilizando atributos de cor e textura. Workshop de Informática Médica – WIM.
Ojala, T., Pietikäinen, M., e Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29(1):51–59.
Oliveira, R. B. et al. (2016). A computational approach for detecting pigmented skin lesions in macroscopic images. Expert Systems with Applications, 61:53–63.
Rosenfield, G. H. e Fitzpatrick-Lins, K. (1986). A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric engineering and remote sensing, 52(2):223–227.
Sánchez-Monedero, J. et al. (2016). Classification of melanoma presence and thickness based on computational image analysis. In International Conference on Hybrid Artificial Intelligence Systems, pages 427–438. Springer.
Shin, H.-C., Roth, H. R., et al. (2016). Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning. IEEE transactions on medical imaging, 35(5):1285–1298.
Silva Júnior, E. R. (2007). Investigação de técnicas de extração e seleção de características e classificadores aplicados ao problema de classificação de dígitos manuscritos de imagens de documentos históricos. 51 f. Monografia (Bacharelado em Engenharia da Computação) — Escola Politécnica de Pernambuco, UFPE, Pernambuco.
Sobel, I. (1970). Camera models and machine perception. Technical report, DTIC Document.
Society, A. C. (2015). Cancer facts & figures 2015. [link]. Acessado em: 2017.
Tamura, H., Mori, S., e Yamawaki, T. (1978). Textural features corresponding to visual perception. IEEE Transactions on Systems, Man, and Cybernetics, 8(6):460–473.
Publicado
02/07/2017
Como Citar
MOURA, Nayara; VERAS, Rodrigo; AIRES, Kelson; SANTOS, Luís; MACHADO, Vinicius.
Proposta de um Descritor Híbrido para Aprimoramento da Identificação Automática de Melanoma. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 17. , 2017, São Paulo.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2017
.
p. 2034-2043.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2017.3721.
